8 views
-/https://github.com/berriai/litellm/issues/26775
GitHub · issue

#26775 [Feature]: LiteLLM Cost Map Langfuse Sync Or enable Lang fuse ingesting

  • State: open
  • Author: @RemeLards
  • Labels: enhancement, stale, SDK

### Check for existing issues

- [x] I have searched the existing issues and checked that my issue is not a duplicate.

### The Feature

As the title says, being able to ingest costs of models not present in default Langfuse model table or being able to sync the cost map with the model table of the langfuse.

### Motivation, pitch

I've tried searching LiteLLM docs and Langfuse docs and saw I could Ingest Langfuse costs, but since I can't access LiteLLM generation, this is not possible. So the only way I've been able to make it work, is to sync (some) of the models present in the cost map to the Langfuse Model Table, so Langfuse can Infer costs. I'm almost sure there's a way but I could not find how to do it, if there's, show me and close the issue, thanks in advance!

### What part of LiteLLM is this about?

SDK (litellm Python package)

### LiteLLM is hiring a founding backend engineer, are you interested in joining us and shipping to all our users?

No

### Twitter / LinkedIn details

_No response_

GitHub resolver

Import GitHub neighbors on demand. Results are saved as system ingests.

Refresh page
vote history (1 events)
#0 of 0 · 31d17h56m14s ago — entered · #import:https:::github.com:berriai:litellm post #3030
The left issue requires cross-system integration, synchronization semantics, compatibility handling, and broader testing; the right is comparatively localized metadata correction with targeted validation.
discussed in #import:https:::github.com:berriai:litellm

ranked child groups

no voted pairs yet in this scope

cli
src
spread
search